Technologies

17 pages, 581 KB

Open AccessCommunication

3D Localization of Near-Field Sources with Symmetric Enhanced Nested Arrays

by Linke Yu, Huayue Wu, Haifen Meng, Zheng Zhou and Hua Chen

Technologies 2025, 13(9), 415; https://doi.org/10.3390/technologies13090415 - 12 Sep 2025

Sparse arrays can effectively reduce antenna cost and implementation complexity. However, most existing research in sparse array design mainly focuses on far-field scenarios, which cannot be directly applied to near-field (NF) source localization, where the delay term and source incident parameters exhibit a [...] Read more.

Sparse arrays can effectively reduce antenna cost and implementation complexity. However, most existing research in sparse array design mainly focuses on far-field scenarios, which cannot be directly applied to near-field (NF) source localization, where the delay term and source incident parameters exhibit a nonlinear relationship. In this paper, employing a symmetric enhanced nested array, a high-precision underdetermined three-dimensional (3D) NF localization method is proposed. Firstly, the symmetry of the array and the fourth-order cumulant are utilized to construct the equivalent virtual far-field (FF) received data. Then, a gridless, sparse, and parametric approach combined with an l₁-singular value decomposition-based pairing procedure is employed to obtain estimates of two paired angles. Finally, a one-dimensional (1D) spectral estimator is applied to obtain the estimate of the range parameter. By analyzing the virtual aperture, the optimal parameter configuration for a given number of elements is obtained. As shown by simulation results, the proposed method can handle underdetermined estimation. Compared with the other algorithms, the proposed algorithm achieves significant improvements in both angular and distance accuracy, with enhancements of 65% and 61.7%, respectively. Full article

(This article belongs to the Topic Advanced Propagation Channel Estimation Techniques for Sixth-Generation (6G) Wireless Communications)

► Show Figures

Figure 1

18 pages, 44725 KB

Open AccessArticle

BCP-YOLOv5: A High-Precision Object Detection Model for Peony Flower Recognition Based on YOLOv5

by Baofeng Ji, Xiaoshuai Hong, Ji Zhang, Chunhong Dong, Fazhan Tao, Gaoyuan Zhang and Huitao Fan

Technologies 2025, 13(9), 414; https://doi.org/10.3390/technologies13090414 - 11 Sep 2025

Abstract

Peony flowers in Luoyang are renowned for their diverse varieties and substantial economic value. However, recognizing multiple peony varieties in natural field conditions remains challenging due to limited datasets and the shortcomings of existing detection models. High intra-class similarity among peony varieties, frequent [...] Read more.

Peony flowers in Luoyang are renowned for their diverse varieties and substantial economic value. However, recognizing multiple peony varieties in natural field conditions remains challenging due to limited datasets and the shortcomings of existing detection models. High intra-class similarity among peony varieties, frequent occlusions, and imbalanced sample quality pose significant challenges to conventional approaches. To address these issues, we propose BCP-YOLOv5, an enhanced YOLOv5-based model designed for peony variety detection. The proposed model incorporates the Vision Transformer with Bi-Level Routing Attention (Biformer) to improve the detection accuracy of occluded targets. Inspired by Focal-EIoU, we redesign the loss function as Focal-CIoU to reduce the impact of low-quality samples and enhance bounding box localization. Additionally, Content-Aware Reassembly of Features (CARAFE) is employed to replace traditional upsampling, further improving performance. The experiments show that BCP-YOLOv5 improves precision by 3.4%, recall by 4.4%, and mAP@0.5 by 4.5% over baseline YOLOv5s. This work fills the gap in multi-variety peony detection and offers a practical, reproducible solution for intelligent agriculture. Full article

► Show Figures

Figure 1

28 pages, 4127 KB

Open AccessFeature PaperArticle

Deep Residual Learning for Face Anti-Spoofing: A Mathematical Framework for Optimized Skip Connections

by Ardak Nurpeisova, Anargul Shaushenova, Oleksandr Kuznetsov, Aidar Ispussinov, Zhazira Mutalova and Akmaral Kassymova

Technologies 2025, 13(9), 413; https://doi.org/10.3390/technologies13090413 - 11 Sep 2025

Abstract

Face anti-spoofing is crucial for protecting biometric authentication systems. Presentation attacks using 3D masks and high-resolution printed images present detection challenges for existing methods. In this paper, we introduce a family of specialized CNN architectures, AttackNet, designed for robust face anti-spoofing with optimized [...] Read more.

Face anti-spoofing is crucial for protecting biometric authentication systems. Presentation attacks using 3D masks and high-resolution printed images present detection challenges for existing methods. In this paper, we introduce a family of specialized CNN architectures, AttackNet, designed for robust face anti-spoofing with optimized residual connections and activation functions. The study includes the development of four architectures: baseline LivenessNet, AttackNetV1 with concatenation-based skip connections, AttackNetV2.1 with optimized activation functions, and AttackNetV2.2 with efficient addition-based residual learning. Our analysis demonstrates that element-wise addition in skip connections reduces parameters from 8.4 M to 4.2 M while maintaining performance. A comprehensive evaluation was conducted on four benchmark datasets: MSSpoof, 3DMAD, CSMAD, and Replay-Attack. Results show high accuracy (approaching 100%) on the 3DMAD, CSMAD, and Replay-Attack datasets. On the more challenging MSSpoof dataset, AttackNetV1 achieved 99.6% accuracy with an HTER of 0.004, outperforming the baseline LivenessNet (94.35% accuracy, 0.056 HTER). Comparative analysis with state-of-the-art methods confirms the superiority of the proposed approach. AttackNetV2.2 demonstrates an optimal balance between accuracy and computational efficiency, requiring 16.1 MB of memory compared to 32.1 MB for other AttackNet variants. Training time analysis shows twice the speed for AttackNetV2.2 compared to AttackNetV1. Architectural ablation studies highlight the crucial role of residual connections, batch normalization, and suitable dropout rates. Statistical significance testing verifies the reliability of the results (p-value < 0.001). The proposed architectures show excellent generalization ability and practical usefulness for real-world deployment in mobile and embedded systems. Full article

(This article belongs to the Special Issue Research on Security and Privacy of Data and Networks)

► Show Figures

Figure 1

36 pages, 1229 KB

Open AccessArticle

Redefining Transactions, Trust, and Transparency in the Energy Market from Blockchain-Driven Technology

by Manuel Uche-Soria, Antonio Martínez Raya, Alberto Muñoz Cabanes and Jorge Moya Velasco

Technologies 2025, 13(9), 412; https://doi.org/10.3390/technologies13090412 - 10 Sep 2025

Abstract

Rapid depletion of fossil fuel reserves forces the global energy sector to transition to sustainable energy sources. Specifically, distributed energy markets have emerged in the renewable energy sector in recent years, partly because blockchain technology is becoming a successful way to promote secure [...] Read more.

Rapid depletion of fossil fuel reserves forces the global energy sector to transition to sustainable energy sources. Specifically, distributed energy markets have emerged in the renewable energy sector in recent years, partly because blockchain technology is becoming a successful way to promote secure and transparent transactions. Using its decentralized structure, transparency, and even pseudonymity, blockchain is increasingly adopted worldwide for large-scale energy trading, peer-to-peer exchanges, project financing, supply chain management, and asset tracking. The research comprehensively analyzes blockchain applications across multiple fields related to energy, bibliographically evaluating their transformative potential. In addition, the study explores the architecture of various blockchain systems, assesses critical security and privacy challenges, and discusses how blockchain can enhance operational efficiency, transparency, and reliability in the energy sector. The paper’s findings provide a roadmap for future developments and the strategic adoption of blockchain technologies in the evolving energy landscape for an effective energy transition. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

19 pages, 3154 KB

Open AccessArticle

Physiologically Explainable Ensemble Framework for Stress Classification via Respiratory Signals

by Chenxi Yang, Siyu Wei, Jianqing Li and Chengyu Liu

Technologies 2025, 13(9), 411; https://doi.org/10.3390/technologies13090411 - 10 Sep 2025

Abstract

This study proposes a physiologically interpretable framework for stress state classification using respiratory signals. The framework aims to assess whether integrating physiologically meaningful features with an interpretable model can enhance both the accuracy and interpretability of stress state classification. First, a 16-parameter feature [...] Read more.

This study proposes a physiologically interpretable framework for stress state classification using respiratory signals. The framework aims to assess whether integrating physiologically meaningful features with an interpretable model can enhance both the accuracy and interpretability of stress state classification. First, a 16-parameter feature set was constructed by extracting rhythm, depth, and nonlinear characteristics of respiratory signals. Subsequently, feature correlations and group differences across stress states were analyzed via heatmaps, multivariate analysis of variance (MANOVA), and box plots. A stacking ensemble model was then designed for three-state classification (normal/stress/meditation). Finally, Shapley additive explanations (SHAP) values were used to quantify feature contributions to classification outcomes. The leave-one-subject-out (LOSO) cross-validation results show that on the wearable stress and affect detection (WESAD) dataset, the model achieves an accuracy of 92.33% and a precision of 93.54%. Furthermore, initial validation shows key respiratory features like breath rate, inspiration time ratio, and expiratory variability coefficient align with autonomic regulation. Key respiratory metrics in other areas like rapid shallow breathing index also play an important role in the stress classification. Notably, increased respiratory depth under a stress state needs further study to clarify its physiological reasons. Overall, this framework enhances physiological interpretability while maintaining competitive performance, offering a promising approach for future applications in multimodal stress monitoring and clinical assessment. Full article

(This article belongs to the Section Assistive Technologies)

► Show Figures

Figure 1

26 pages, 24376 KB

Open AccessArticle

Enhancing Traffic Safety and Efficiency with GOLC: A Global Optimal Lane-Changing Model Integrating Real-Time Impact Prediction

by Jia He, Yanlei Hu, Wen Zhang, Zhengfei Zheng, Wenqi Lu and Tao Wang

Technologies 2025, 13(9), 410; https://doi.org/10.3390/technologies13090410 - 10 Sep 2025

Abstract

Lane-changing maneuvers critically influence traffic flow and safety. This study introduces the Global Optimal Lane-Changing (GOLC) model, a framework that optimizes decisions by quantitatively predicting their systemic effects on surrounding traffic. Unlike traditional models that focus on immediate neighbors, the GOLC model integrates [...] Read more.

Lane-changing maneuvers critically influence traffic flow and safety. This study introduces the Global Optimal Lane-Changing (GOLC) model, a framework that optimizes decisions by quantitatively predicting their systemic effects on surrounding traffic. Unlike traditional models that focus on immediate neighbors, the GOLC model integrates a kinematic wave model to precisely quantify the spatiotemporal impacts on the entire affected platoon, striking a balance between local vehicle actions and global traffic efficiency. Implemented in the Simulation of Urban Mobility (SUMO) environment, the GOLC model is evaluated against benchmark models Minimizing Overall Braking Induced by Lane Changes (MOBIL) and SUMO LC2013. Comparative evaluations demonstrate the GOLC model’s superior performance. In a three-lane scenario, the GOLC model significantly enhances traffic efficiency, reducing average delay by 3.4% to 46.8% compared to MOBIL under medium- to high-flow conditions. It also fosters a safer environment by reducing unnecessary lane changes by 1.1 times compared to the LC2013 model. In incident scenarios, the GOLC model shows greater adaptability, achieving higher average speeds and lower travel times while minimizing speed dispersion and deceleration. These findings validate the effectiveness of embedding macroscopic traffic theory into microscopic driving decisions. The model’s unique strength lies in its ability to predict and minimize the collective negative impact on all affected vehicles, representing a significant step towards real-world implementation in Advanced Driver-Assistance Systems (ADAS) and enhancing safety in next-generation intelligent transportation systems. Full article

(This article belongs to the Special Issue Advanced Intelligent Driving Technology)

► Show Figures

Figure 1

24 pages, 7601 KB

Open AccessArticle

Network Intrusion Detection Integrating Feature Dimensionality Reduction and Transfer Learning

by Hui Wang, Wei Jiang, Junjie Yang, Zitao Xu and Boxin Zhi

Technologies 2025, 13(9), 409; https://doi.org/10.3390/technologies13090409 - 10 Sep 2025

Abstract

In the Internet era, network malicious intrusion behaviors occur frequently and network intrusion detection is increasingly in demand. Addressing the challenges of high-dimensional data, nonlinearity and noisy network traffic data in network intrusion detection, a net-work intrusion detection model is proposed in this [...] Read more.

In the Internet era, network malicious intrusion behaviors occur frequently and network intrusion detection is increasingly in demand. Addressing the challenges of high-dimensional data, nonlinearity and noisy network traffic data in network intrusion detection, a net-work intrusion detection model is proposed in this paper. Firstly, a hybrid multi-model feature selection and kernel-based dimensionality reduction algorithm is proposed to map high-dimensional features to low-dimensional space to achieve feature dimensionality reduction and enhance nonlinear differentiability. Then the semantic feature mapping is introduced to convert the low-dimensional features into color images which represent distinct data characteristic. For classifying these images, an integrated convolutional neural network is constructed. Moreover, sub-model fine-tuning is performed through transfer learning and weights are assigned to improve the performance of multi-classification detection. Experiments on the UNSW-NB15 and CICIDS 2017 datasets show that the proposed model achieves accuracies of 99.99% and 99.96%. The F1-scores of 99.98% and 99.91% are achieved respectively. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

8 pages, 181 KB

Open AccessEditorial

Empowering Independence: The Role of Assistive Technologies in Enhancing Quality of Life

by Daniele Giansanti

Technologies 2025, 13(9), 408; https://doi.org/10.3390/technologies13090408 - 8 Sep 2025

Abstract

Assistive technologies are increasingly central to improving quality of life across various settings, from rehabilitation to ongoing care [...] Full article

(This article belongs to the Special Issue Assistive Technologies in Care and Rehabilitation: Research, Developments, and International Initiatives)

14 pages, 2076 KB

Open AccessArticle

User Evaluation of Head-Level Obstacle Detector for Visually Impaired

by Iva Klimešová, Ján Lešták, Karel Hána, Tomáš Veselý and Pavel Smrčka

Technologies 2025, 13(9), 407; https://doi.org/10.3390/technologies13090407 - 6 Sep 2025

Abstract

The white cane is a reliable and often-used assistive aid; however, it does not protect against obstacles at the head level. We designed and built an ultrasonic-based obstacle detector with a limited detection field in front of the head. The detector is located [...] Read more.

The white cane is a reliable and often-used assistive aid; however, it does not protect against obstacles at the head level. We designed and built an ultrasonic-based obstacle detector with a limited detection field in front of the head. The detector is located on the chest and can be mounted on backpack straps or around the neck. We have performed testing with 74 blind people and their instructors. Blind people used the device for three to four weeks in their regular lives, and instructors tested it by themselves or with their clients. The testing showed that individualization by the type of mounting is helpful. The needed detection distance depends on the situation and the speed of movement. In total, 70% of the users were satisfied with the distance options 80 cm, 110 cm, and 140 cm. 81% of the testers were satisfied, or somewhat satisfied, with the sliding switches to control. It is simple, and its position (setting) can be detected by touch. The testers see the benefit of using the device, especially in unknown environments (outdoor and indoor), primarily because of the increased safety by movement (64%) or the feeling of security (41%). Full article

(This article belongs to the Section Assistive Technologies)

► Show Figures

Figure 1

20 pages, 2584 KB

Open AccessArticle

Dynamic Updating of Geological Models by Directly Interpolating Geological Logging Data

by Deyun Zhong, Zhaohao Wu, Liguan Wang and Jianhong Chen

Technologies 2025, 13(9), 406; https://doi.org/10.3390/technologies13090406 - 6 Sep 2025

Abstract

Traditional orebody modeling methods struggle to efficiently integrate new geological data. Therefore, we propose a novel framework for dynamically updating 3D geological models by directly interpolating geological logging data. The core innovation lies in the innovative interpolation of raw interpreted cross polylines into [...] Read more.

Traditional orebody modeling methods struggle to efficiently integrate new geological data. Therefore, we propose a novel framework for dynamically updating 3D geological models by directly interpolating geological logging data. The core innovation lies in the innovative interpolation of raw interpreted cross polylines into an implicit scalar field representation without intermediate explicit surface extraction or manual remodeling. To obtain reliable vectorized polylines, we developed image recognition and digitization techniques that are based on the pattern recognition of geological sketches. Moreover, different from existing implicit techniques, we present an improved approach to interpolate complex cross polylines that are dynamically based on the improved principal component analysis. The method allows specifying a priori constraints to adjust the erroneous estimated normal to improve the reliability of the normal estimation results of cross-contour polylines. The a priori information can be combined into the normal estimation algorithm to update the normals of the corresponding adjacent contour polylines in the process of normal estimation at the intersection points and in the process of normal propagation. By leveraging the radial basis functions-based spatial interpolators, the method continuously assimilates incremental geological observations into the interpolation constraints to update the implicit model. Case studies demonstrate a reduction in the modeling cycle time compared to conventional explicit methods while maintaining geologically coherent boundaries. The framework significantly enhances decision agility in resource estimation and mine planning workflows by bridging geological interpretation and dynamic model iteration. Full article

► Show Figures

Figure 1

30 pages, 6751 KB

Open AccessArticle

Web System for Solving the Inverse Kinematics of 6DoF Robotic Arm Using Deep Learning Models: CNN and LSTM

by Mayra A. Torres-Hernández, Teodoro Ibarra-Pérez, Eduardo García-Sánchez, Héctor A. Guerrero-Osuna, Luis O. Solís-Sánchez and Ma. del Rosario Martínez-Blanco

Technologies 2025, 13(9), 405; https://doi.org/10.3390/technologies13090405 - 5 Sep 2025

Abstract

This work presents the development of a web system using deep learning (DL) neural networks to solve the inverse kinematics problem of the Quetzal robotic arm, designed for academic and research purposes. Two architectures, LSTM and CNN, were designed, trained, and evaluated using [...] Read more.

This work presents the development of a web system using deep learning (DL) neural networks to solve the inverse kinematics problem of the Quetzal robotic arm, designed for academic and research purposes. Two architectures, LSTM and CNN, were designed, trained, and evaluated using data generated through the Denavit–Hartenberg (D-H) model, considering the robot’s workspace. The evaluation employed the mean squared error (MSE) as the loss metric and mean absolute error (MAE) and accuracy as performance metrics. The CNN model, featuring four convolutional layers and an input of 4 timesteps, achieved the best overall performance (95.9% accuracy, MSE of 0.003, and MAE of 0.040), significantly outperforming the LSTM model in training time. A hybrid web application was implemented, allowing offline training and real-time online inference under one second via an interactive interface developed with Streamlit 1.16. The solution integrates tools such as TensorFlow™ 2.15, Python 3.10, and Anaconda Distribution 2023.03-1, ensuring portability to fog or cloud computing environments. The proposed system stands out for its fast response times (1 s), low computational cost, and high scalability to collaborative robotics environments. It is a viable alternative for applications in educational or research settings, particularly in projects focused on industrial automation. Full article

(This article belongs to the Special Issue AI Robotics Technologies and Their Applications)

► Show Figures

Figure 1

34 pages, 3473 KB

Open AccessArticle

Workspace Definition in Parallelogram Manipulators: A Theoretical Framework Based on Boundary Functions

by Luis F. Luque-Vega, Jorge A. Lizarraga, Dulce M. Navarro, Jose R. Navarro, Rocío Carrasco-Navarro, Emmanuel Lopez-Neri, Jesús Antonio Nava-Pintor, Fabián García-Vázquez and Héctor A. Guerrero-Osuna

Technologies 2025, 13(9), 404; https://doi.org/10.3390/technologies13090404 - 5 Sep 2025

Abstract

Robots with parallelogram mechanisms are widely employed in industrial applications due to their mechanical rigidity and precise motion control. However, the analytical definition of feasible workspace regions free from self-collisions remains an open challenge, especially considering the nonlinear and composite nature of such [...] Read more.

Robots with parallelogram mechanisms are widely employed in industrial applications due to their mechanical rigidity and precise motion control. However, the analytical definition of feasible workspace regions free from self-collisions remains an open challenge, especially considering the nonlinear and composite nature of such regions. This work introduces a mathematical model grounded in a collision theorem that formalizes boundary functions based on joint variables and geometric constraints. These functions explicitly define the envelope of safe configurations by evaluating relative positions between critical structural components. Using the MinervaBotV3 as a case study, the symbolic joint-space boundaries and their corresponding geometric regions in both 2D and 3D are computed and visualized. The feasible region is refined through centroid-based scaling to introduce safety margins and avoid singularities. The results show that this framework enables analytically continuous workspace representations, improving trajectory planning and reliability in constrained environments. Future work will extend this method to spatial mechanisms and real-time implementations in hybrid robotic systems. Full article

(This article belongs to the Special Issue Collaborative Robotics and Human-AI Interactions)

► Show Figures

Figure 1

26 pages, 3749 KB

Open AccessArticle

Synthesis of Pectin Hydrogels from Grapefruit Peel for the Adsorption of Heavy Metals from Water

by Vinusiya Vigneswararajah, Nirusha Thavarajah and Xavier Fernando

Technologies 2025, 13(9), 403; https://doi.org/10.3390/technologies13090403 - 5 Sep 2025

Abstract

The increasing presence of heavy metals in aquatic environments, driven by the production of industrial waste and consumer products, poses serious environmental and health risks due to their toxicity and persistence. Copper (Cu(II)) and nickel (Ni(II)) are particularly harmful, with high concentrations linked [...] Read more.

The increasing presence of heavy metals in aquatic environments, driven by the production of industrial waste and consumer products, poses serious environmental and health risks due to their toxicity and persistence. Copper (Cu(II)) and nickel (Ni(II)) are particularly harmful, with high concentrations linked to neurological, dermatological and carcinogenic effects. This proof-of-concept study explores the synthesis of sustainable hydrogels derived from grapefruit peel (biosorbents) for the adsorption of Cu(II) and Ni(II) from aqueous solutions. Pectin was extracted from the peels and was used to synthesize pectin-based hydrogels (PH) and pectin hydrogel metal–organic frameworks (PHM composites). The hydrogels were characterized using FT-IR, SEM, diameter size and water absorption capacity. Lyophilized hydrogels were significantly smaller than their wet counterparts, and adsorption performance was analyzed using FAAS. PHs demonstrated high Cu(II) removal efficiency, achieving 95.11% adsorption and 97.75 mg/g capacity at pH 5. PHM composites showed comparable Cu(II) adsorption with a maximum capacity of 67.53 mg/g. Notably, PHs also exhibited rapid Ni(II) adsorption, reaching 92.62% efficiency and 28.189 mg/g capacity within one minute. These findings highlight the potential of pectin-based hydrogels as an effective, low-cost and environmentally friendly method for heavy metal remediation in water. Full article

(This article belongs to the Special Issue Technological Advances in Science, Medicine, and Engineering 2025)

► Show Figures

Figure 1

27 pages, 1630 KB

Open AccessArticle

Hybrid LSTM–FACTS Control Strategy for Voltage and Frequency Stability in EV-Penetrated Microgrids

by Paul Arévalo-Cordero, Félix González, Andrés Martínez, Diego Zarie, Augusto Rodas, Esteban Albornoz, Danny Ochoa-Correa and Darío Benavides

Technologies 2025, 13(9), 402; https://doi.org/10.3390/technologies13090402 - 4 Sep 2025

Abstract

This paper proposes a real-time energy management strategy for low-voltage microgrids that combines short-horizon forecasting with a rule-based supervisory controller to coordinate battery energy storage usage and reactive power support provided by flexible alternating current transmission technologies. The central contribution is the forecast-informed, [...] Read more.

This paper proposes a real-time energy management strategy for low-voltage microgrids that combines short-horizon forecasting with a rule-based supervisory controller to coordinate battery energy storage usage and reactive power support provided by flexible alternating current transmission technologies. The central contribution is the forecast-informed, joint orchestration of active charging and reactive power dispatch to regulate voltage and preserve stability under large photovoltaic variability and uncertain electric vehicle demand. The work also introduces a resilience response index that quantifies performance under external disturbances, forecasting delays, and increasing levels of electric-vehicle integration. Validation is carried out through time-domain numerical simulations in MATLAB/Simulink using realistic solar irradiance and electric vehicle charging profiles. The results show that the coordinated strategy reduces voltage deviation events, maintains stable operation across a wide range of scenarios, and enables electric vehicle charging to be supplied predominantly by renewable generation. Sensitivity analysis further indicates that support from flexible alternating current devices becomes particularly decisive at high charging demand and in the presence of forecasting latency, underscoring the practical value of the proposed approach for distribution-level microgrids. Full article

► Show Figures

Graphical abstract

27 pages, 6135 KB

Open AccessArticle

A Unified Deep Learning Framework for Robust Multi-Class Tumor Classification in Skin and Brain MRI

by Mohamed A. Sayedelahl, Ahmed G. Gad, Reham M. Essa, Zakaria G. Hussein and Amr A. Abohany

Technologies 2025, 13(9), 401; https://doi.org/10.3390/technologies13090401 - 3 Sep 2025

Abstract

Early detection of cancer is critical for effective treatment, particularly for aggressive malignancies like skin cancer and brain tumors. This research presents an integrated deep learning approach combining augmentation, segmentation, and classification techniques to identify diverse tumor types in skin lesions and brain [...] Read more.

Early detection of cancer is critical for effective treatment, particularly for aggressive malignancies like skin cancer and brain tumors. This research presents an integrated deep learning approach combining augmentation, segmentation, and classification techniques to identify diverse tumor types in skin lesions and brain MRI scans. Our method employs a fine-tuned InceptionV3 convolutional neural network trained on a multi-modal dataset comprising dermatoscopy images from the Human Against Machine archive and brain MRI scans from the ISIC 2023 repository. To address class imbalance, we implement advanced preprocessing and Generative Adversarial Network (GAN)-based augmentation. The model achieves 97% accuracy in classifying images across ten categories: seven skin cancer types, multiple brain tumor variants, and an “undefined” class. These results suggest clinical applicability for multi-cancer detection. Full article

(This article belongs to the Special Issue Application of Artificial Intelligence in Medical Image Analysis)

► Show Figures

Figure 1

22 pages, 763 KB

Open AccessArticle

Optimizing TSCH Scheduling for IIoT Networks Using Reinforcement Learning

by Sahar Ben Yaala, Sirine Ben Yaala and Ridha Bouallegue

Technologies 2025, 13(9), 400; https://doi.org/10.3390/technologies13090400 - 3 Sep 2025

Abstract

In the context of industrial applications, ensuring medium access control is a fundamental challenge. Industrial IoT devices are resource-constrained and must guarantee reliable communication while reducing energy consumption. The IEEE 802.15.4e standard proposed time-slotted channel hopping (TSCH) to meet the requirements of the [...] Read more.

In the context of industrial applications, ensuring medium access control is a fundamental challenge. Industrial IoT devices are resource-constrained and must guarantee reliable communication while reducing energy consumption. The IEEE 802.15.4e standard proposed time-slotted channel hopping (TSCH) to meet the requirements of the industrial Internet of Things. TSCH relies on time synchronization and channel hopping to improve performance and reduce energy consumption. Despite these characteristics, configuring an efficient schedule under varying traffic conditions and interference scenarios remains a challenging problem. The exploitation of reinforcement learning (RL) techniques offers a promising approach to address this challenge. AI enables TSCH to dynamically adapt its scheduling based on real-time network conditions, making decisions that optimize key performance criteria such as energy efficiency, reliability, and latency. By learning from the environment, reinforcement learning can reconfigure schedules to mitigate interference scenarios and meet traffic demands. In this work, we compare various reinforcement learning (RL) algorithms in the context of the TSCH environment. In particular, we evaluate the deep Q-network (DQN), double deep Q-network (DDQN), and prioritized DQN (PER-DQN). We focus on the convergence speed of these algorithms and their capacity to adapt the schedule. Our results show that the PER-DQN algorithm improves the packet delivery ratio and achieves faster convergence compared to DQN and DDQN, demonstrating its effectiveness for dynamic TSCH scheduling in Industrial IoT environments. These quantifiable improvements highlight the potential of prioritized experience replay to enhance reliability and efficiency under varying network conditions. Full article

(This article belongs to the Section Information and Communication Technologies)

► Show Figures

Figure 1

15 pages, 4611 KB

Open AccessArticle

Real-Time Prediction of Foot Placement and Step Height Using Stereo Vision Enhanced by Ground Object Awareness

by Chulyong Lim, Jaewon Baek, Junhee Han, Giuk Lee and Woochul Nam

Technologies 2025, 13(9), 399; https://doi.org/10.3390/technologies13090399 - 3 Sep 2025

Abstract

Foot placement position (FP) and step height (SH) are needed to control walking-assistive systems on uneven terrain. This study proposes a novel model that predicts FP and SH before a user takes a step. The model uses a stereo vision system mounted on [...] Read more.

Foot placement position (FP) and step height (SH) are needed to control walking-assistive systems on uneven terrain. This study proposes a novel model that predicts FP and SH before a user takes a step. The model uses a stereo vision system mounted on the upper body and adapts to various terrains by incorporating foot motions and terrain object information. First, FP was predicted by visually tracking foot positions and was corrected based on the types and locations of objects on the ground. Then, SH was estimated using depth maps captured by an RGB-D stereo camera. To predict SH, several RGB-D frames were considered with homography, feature matching, and image transformation. The results show that the heatmap trajectory improved FP prediction on the flat-walking dataset, reducing the root mean square error of FP from 20.89 to 17.70 cm. Furthermore, incorporating object preference significantly improved FP prediction, resulting in an accuracy improvement from 52.57% to 78.01% in identifying the object a user stepped on. The mean absolute error of SH was calculated to be 7.65 cm in scenes containing rocks and puddles. The proposed model can enhance the control of walking-assistive systems in complex environments. Full article

(This article belongs to the Special Issue Advancements in Medical and Assistive Technologies Using Artificial Intelligence and Deep Learning Techniques)

► Show Figures

Figure 1

23 pages, 5879 KB

Open AccessArticle

CAD Analysis of 3D Printed Parts for Material Extrusion—Pre-Processing Optimization Method

by Andrei Mario Ivan, Cozmin Adrian Cristoiu and Lidia Florentina Parpala

Technologies 2025, 13(9), 398; https://doi.org/10.3390/technologies13090398 - 3 Sep 2025

Abstract

Free form fabrication (FFF), also known as fused deposition modeling (FDM), is a widespread and accessible method for prototyping. Parts a with lattice structure having functional roles as mechanism elements is becoming more common. In the research field, the mechanical characteristics as well [...] Read more.

Free form fabrication (FFF), also known as fused deposition modeling (FDM), is a widespread and accessible method for prototyping. Parts a with lattice structure having functional roles as mechanism elements is becoming more common. In the research field, the mechanical characteristics as well as optimization methods for manufacturing these parts are major points of interest. One of the major aspects of FFF is part orientation during print, as it has influence over a wide range of variables, from tensile strength to surface quality and material consumption. For parts with a lattice structure, the printing orientation is important not only as a factor that influences the characteristics of the part itself, but also as a factor that determines the support requirements. However, due to the complex lattice structure, removing supports from these parts can be a challenging task. This study focuses on analyzing the reliability of available CAD optimization methods for FFF pre-processing. The analysis is performed using the Design for Additive Manufacturing module included in the Siemens NX software, version NX2406. The efficiency of CAD optimization was observed by taking into account the material consumption, printing times, surface quality, and support requirements. The study methods were based on the comparative analysis approach. The case studies used for the comparative analysis consider two-part inner structures: the solid structure approach with a rectilinear infill and the lattice structure approach. Full article

(This article belongs to the Section Innovations in Materials Science and Materials Processing)

► Show Figures

Figure 1

26 pages, 2682 KB

Open AccessArticle

A Novel Membrane Dehumidification Technology Using a Vacuum Mixing Condenser and a Multiphase Pump

by Jing Li, Chang Zhou, Xiaoli Ma, Xudong Zhao, Xiang Xu, Semali Perera, Joshua Nicks and Barry Crittenden

Technologies 2025, 13(9), 397; https://doi.org/10.3390/technologies13090397 - 3 Sep 2025

Abstract

Vacuum membrane-based air dehumidification (MAD) is potentially more efficient than refrigeration cycles. Air permeance through a membrane is inevitable, especially when there is a large pressure difference between the supply and permeate sides. Given the high specific gas volume under vacuum conditions, removing [...] Read more.

Vacuum membrane-based air dehumidification (MAD) is potentially more efficient than refrigeration cycles. Air permeance through a membrane is inevitable, especially when there is a large pressure difference between the supply and permeate sides. Given the high specific gas volume under vacuum conditions, removing the permeating air from the dehumidifier is crucial for the stable operation of the vacuum compressor. Energy-efficient air removal techniques are still lacking, thereby hindering the development of MAD technology. This paper proposes a novel MAD approach using a vacuum mixing condenser. The cooling water directly condenses moisture from the vacuum compressor without any heat exchanger. The permeating air and water mixture in the condenser then experiences a quasi-isothermal pressurization process through a multiphase pump, enabling continuous dehumidification and air removal with low power consumption. The fundamentals of the proposed approach are illustrated, and mathematical models are built. Influences of air permeance rate, cooling water flow rate, condenser pressure, membrane area, and gravitational work are investigated. The results show that a COP of 8~12 is achievable to dehumidify air to 50%RH, 25 °C. The vacuum compressor consumes about 80% of the power. A low air permeance rate, low condenser pressure, large membrane area, and high gravitational work positively impact the COP, while the cooling water flow rate has a more complex effect. The proposed dehumidifier can use less selective membranes for higher permeability and cost-effectiveness. Full article

(This article belongs to the Section Environmental Technology)

► Show Figures

Figure 1

Journal Description

Technologies

Latest Articles

Journal Menu

Journal Browser

Highly Accessed Articles

Latest Books

E-Mail Alert

News

Topics

Conferences

Special Issues

Topical Collections

Further Information

Guidelines

MDPI Initiatives

Follow MDPI